A set of Cursor rules for automating job searches on BOSS直聘, a Chinese recruiting platform. It describes commands for searching jobs, matching them to a résumé, improving a résumé, and sending messages.

Searching for jobs by role and city, matching listings to a résumé, generating personalized greeting messages, optimizing a résumé for a job description, and sending an approved message.

It organizes a job-search workflow around the candidate’s keywords, location, résumé, and selected jobs. It also requires confirmation before a message is sent.

How xiarongwen/boss-auto-job configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to xiarongwen/boss-auto-job. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/xiarongwen/boss-auto-job/main/.cursorrules

Clone the repo

git clone --depth 1 https://github.com/xiarongwen/boss-auto-job

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/rules/xiarongwen/boss-auto-job/cursorrules.svg)](https://agentmods.dev/rules/xiarongwen/boss-auto-job/cursorrules)

Your own site

<a href="https://agentmods.dev/rules/xiarongwen/boss-auto-job/cursorrules"><img src="https://agentmods.dev/badge/rules/xiarongwen/boss-auto-job/cursorrules.svg" alt="Measured on agentmods" height="20"></a>

Per session 989 This file is loaded in full into every session.

When invoked 989 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00989	$0.00989
Opus 5	$0.00495	$0.00495
Sonnet 5	$0.00198	$0.00198
Haiku 4.5	$0.00099	$0.00099

Measured 6d ago against content hash 65005a9ea252, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cursorrules scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursorrules · 110 lines

What it actually says

Boss Auto Job — Skill Instructions

在 BOSS 直聘上自动搜索职位、匹配简历、生成打招呼语、发送消息。

何时使用

当用户提到以下关键词时激活此技能：

找工作、求职、投简历、看机会
BOSS直聘、BOSS、招聘
搜索职位、发消息、打招呼
简历匹配

前置条件

pip install "camoufox[geoip]" && camoufox fetch

简历文件：~/.hermes/credentials/resume.txt

工具

项目路径下有一个 boss CLI，支持以下命令：

搜索职位

./boss search "关键词" --city 深圳 --area 南山 --pages 2

--city: 城市名（北京/上海/深圳/杭州/成都/广州/南京/武汉/西安/苏州/天津）或城市代码
--area: 区域过滤，如南山、海淀、朝阳
--pages: 页数（默认1，最多3）

搜索 + 简历匹配

./boss search "AI前端" --city 深圳 --match --top 5

搜索 + 匹配 + 自动发送

./boss search "Agent应用开发" --city 深圳 --match --send --top 3

发送消息

./boss send <job_id> "你好，我对这个职位很感兴趣"

其他

./boss optimize <job_id> <resume.pdf>   # 根据JD优化简历（支持PDF/Word）
./boss resume       # 查看简历
./boss cities       # 查看城市代码

工作流程

当用户说"帮我找XX方面的工作"时：

理解需求 — 确认关键词、城市、区域
搜索 — ./boss search "关键词" --city 城市 --area 区域
匹配 — 如果用户有简历，加 --match --top N
展示结果 — 列出匹配度最高的职位，让用户选择
生成招呼语 — Agent 根据 JD + 简历内容直接生成个性化招呼语（见下方规则）
确认发送 — 让用户确认后再发（不要自动发！）
发送 — ./boss send <job_id> "招呼语"

招呼语生成规则

不使用固定模板。 Agent 根据每个职位的 JD 和候选人简历直接生成个性化招呼语。

从 JD 提取 2-3 个关键需求，与简历中的对应经验/技能匹配
语气自然真诚，像在和招聘者对话，不要像在念简历
不要以"您好"千篇一律开头，用更自然的方式切入
体现对该具体公司/岗位的兴趣（从 JD 中提取线索）
总长度 80-150 个中文字符
结尾礼貌地表达沟通意愿
每条消息都应该是独特的，体现这个 JD 和这份简历的特定匹配点

安全规则（必须遵守）

情况	行动
Code 0	正常处理
Code 37	自动生成 zp_stoken，重试 1 次
Code 36	立即停止，告诉用户"请在浏览器中打开 zhipin.com 完成验证后告诉我"
Code 32	立即停止，告诉用户"请在浏览器中完成验证，并手动发一条消息后告诉我"
Code 1006	等待 10 秒重试

绝不重试 Code 36/32，否则会升级封禁。

频率限制

搜索间隔：3-5 秒
发送间隔：5 秒
单次搜索：最多 3 页
单次发送：最多 5 条
每日发送：不超过 20 条

技术文档

REVERSE_ENGINEERING.md — BOSS 风控逆向分析
BYPASS_SOLUTION.md — 绕过方案
SKILL.md — 完整技术文档

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 110 lines · 989 tokens per session scan A 65005a9ea252

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository xiarongwen/boss-auto-job (21 stars, last pushed 4mo ago), licensed MIT. It adds 989 tokens to every session, about $0.0049 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Research

boss-auto-job: Cursor rule for Cursor